20 papers
PatternDex: Learning Interaction Patterns to Guide Reinforcement Learning of Bimanual Dexterous Manipulation of Articulated Objects
David Minkwan Kim, Runfa Blark Li, Beckham Po-Ju Lee +2
In this paper, we develop a method that enables bimanual dexterous hands to manipulate articulated objects with a high success rate without suffering from an embodiment gap. We obs…
Unified Agent: Managing Interactions across Devices
Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei +2
As capabilities rapidly increase, AI agents can move from running inside one app to acting across a user's devices over time. Yet existing agent systems still fall short in this sc…
DexFuture: Hierarchical Future-State Visuomotor Targeting for Bimanual Dexterous Tool Use
Runfa Blark Li, Kuang-Ting Tu, Nikola Raicevic +6
Bimanual dexterous tool use remains challenging for robots due to high-dimensional hand configurations and complex hand-tool-object dynamics and contact. Most existing control poli…
PhysGraph: Physically-Grounded Graph-Transformer Policies for Bimanual Dexterous Hand-Tool-Object Manipulation
Runfa Blark Li, David Kim, Xinshuang Liu +7
Bimanual dexterous manipulation for tool use remains a formidable challenge in robotics due to the high-dimensional state space and complicated contact dynamics. Existing methods n…
HumanOrbit: 3D Human Reconstruction as 360° Orbit Generation
Keito Suzuki, Kunyao Chen, Lei Wang +5
We present a method for generating a full 360° orbit video around a person from a single input image. Existing methods typically adapt image-based diffusion models for multi-view s…
Consistency-Preserving Diverse Video Generation
Xinshuang Liu, Runfa Blark Li, Truong Nguyen
Text-to-video generation is expensive, so only a few samples are typically produced per prompt. In this low-sample regime, maximizing the value of each batch requires high cross-vi…
A Shared-Autonomy Construction Robotic System for Overhead Works
David Minkwan Kim, K. M. Brian Lee, Yong Hyeok Seo +11
We present the ongoing development of a robotic system for overhead work such as ceiling drilling. The hardware platform comprises a mobile base with a two-stage lift, on which a b…
Score-Regularized Joint Sampling with Importance Weights for Flow Matching
Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei +1
Flow matching models effectively represent complex distributions, yet estimating expectations of functions of their outputs remains challenging under limited sampling budgets. Inde…
Image-Conditioned 3D Gaussian Splat Quantization
Xinshuang Liu, Runfa Blark Li, Keito Suzuki +1
3D Gaussian Splatting (3DGS) has attracted considerable attention for enabling high-quality real-time rendering. Although 3DGS compression methods have been proposed for deployment…
WaveletGaussian: Wavelet-domain Diffusion for Sparse-view 3D Gaussian Object Reconstruction
Hung Nguyen, Runfa Li, An Le +1
3D Gaussian Splatting (3DGS) has become a powerful representation for image-based object reconstruction, yet its performance drops sharply in sparse-view settings. Prior works addr…
OpenHuman4D: Open-Vocabulary 4D Human Parsing
Keito Suzuki, Bang Du, Runfa Blark Li +5
Understanding dynamic 3D human representation has become increasingly critical in virtual and extended reality applications. However, existing human part segmentation methods are c…
DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splatting
Hung Nguyen, Runfa Li, An Le +1
Sparse-view 3D Gaussian Splatting (3DGS) presents significant challenges in reconstructing high-quality novel views, as it often overfits to the widely-varying high-frequency (HF)…
From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splatting
Hung Nguyen, An Le, Runfa Li +1
3D Gaussian Splatting has emerged as a powerful approach in novel view synthesis, delivering rapid training and rendering but at the cost of an ever-growing set of Gaussian primiti…
DynaGSLAM: Real-Time Gaussian-Splatting SLAM for Online Rendering, Tracking, Motion Predictions of Moving Objects in Dynamic Scenes
Runfa Blark Li, Mahdi Shaghaghi, Keito Suzuki +8
Simultaneous Localization and Mapping (SLAM) is one of the most important environment-perception and navigation algorithms for computer vision, robotics, and autonomous cars/drones…
Open-Vocabulary Semantic Part Segmentation of 3D Human
Keito Suzuki, Bang Du, Girish Krishnan +3
3D part segmentation is still an open problem in the field of 3D vision and AR/VR. Due to limited 3D labeled data, traditional supervised segmentation methods fall short in general…
GlossGau: Efficient Inverse Rendering for Glossy Surface with Anisotropic Spherical Gaussian
Bang Du, Runfa Blark Li, Chen Du +1
The reconstruction of 3D objects from calibrated photographs represents a fundamental yet intricate challenge in the domains of computer graphics and vision. Although neural recons…
SplatSDF: Boosting SDF-NeRF via Architecture-Level Fusion with Gaussian Splats
Runfa Blark Li, Keito Suzuki, Bang Du +3
Signed distance-radiance field (SDF-NeRF) is a promising environment representation that offers both photo-realistic rendering and geometric reasoning such as proximity queries for…
MonoSelfRecon: Purely Self-Supervised Explicit Generalizable 3D Reconstruction of Indoor Scenes from Monocular RGB Views
Runfa Li, Upal Mahbub, Vasudev Bhaskaran +1
Current monocular 3D scene reconstruction (3DR) works are either fully-supervised, or not generalizable, or implicit in 3D representation. We propose a novel framework - MonoSelfRe…
SM3D: Simultaneous Monocular Mapping and 3D Detection
Runfa Li, Truong Nguyen
Mapping and 3D detection are two major issues in vision-based robotics, and self-driving. While previous works only focus on each task separately, we present an innovative and effi…
MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene FlowEstimation with Monocular Images
Runfa Li, Truong Nguyen
Real-scale scene flow estimation has become increasingly important for 3D computer vision. Some works successfully estimate real-scale 3D scene flow with LiDAR. However, these ubiq…